multi-agent-improve

Community

Automate multi-agent system improvement classification and routing.

AuthorAesopScott
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the classification and routing of evidence and findings into improvements for a multi-agent system, streamlining the M11 Improve phase after M10 Deploy/Observe.

Core Features & Use Cases

  • Evidence Classification: Automatically classify evidence, incidents, traces, eval failures, user feedback, and operator findings.
  • Improvement Routing: Route classified findings across M2-M10 and child APS phases for improvement.
  • Use Case: After deploying a multi-agent system, use this Skill to classify evidence and incidents, then route them to the appropriate phase for improvement, such as M2 roster, M3 contracts, or M4 coordination.

Quick Start

Use the /multi-agent-improve command to initiate the process of classifying and routing improvements for your multi-agent system.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: multi-agent-improve
Download link: https://github.com/AesopScott/central/archive/main.zip#multi-agent-improve

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.